# dataflowr/notebooks

code for deep learning courses

Repository: https://github.com/dataflowr/notebooks
Canonical: https://ross.abutalabs.com/products/dataflowr-notebooks
Homepage: https://dataflowr.github.io/website/
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: deep-learning, pytorch, tutorials
Last push: 2026-05-29T17:51:18+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 84, release rhythm 35, longevity 100
- inputs: {"age_days": 2914, "days_push": 96, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1268, forks 333 (observed 2026-08-28T04:04:11.567767+00:00)

## What it is
Jupyter notebook code and practicals for the Dataflowr 'Deep Learning DIY' course, covering PyTorch tensors, autodiff, CNNs, optimization, and more. It accompanies the free online course taught at École Polytechnique, with solutions to all practicals.

## Use cases
- learn deep learning from scratch with pytorch
- find practical exercises for training neural networks
- understand automatic differentiation and backpropagation
- study convolutional neural networks with worked notebooks
- self-study a university-level deep learning course
- reproduce experiments from recent deep learning papers

## When to choose
- you want a structured, hands-on PyTorch course with solutions
- you prefer learning through notebooks rather than high-level APIs
- you need free course material runnable on Colab without a GPU

## When to avoid
- you need a production deep learning framework or library
- you want TensorFlow or high-level API tutorials
- you need a maintained software package rather than course code

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning, developer-tools
- domain: deep-learning, machine-learning, tutorials, education
- platform: python, cross-platform
- tags: pytorch, jupyter-notebooks, course-material, dataflowr, self-paced-learning

## Member repositories
- dataflowr/notebooks (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.567767+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:37.129551+00:00, confidence not recorded.
  - readme: https://github.com/dataflowr/notebooks (fetched 2026-08-28T04:04:11.567767+00:00, sha 6edbd2b29e88)
  - homepage: https://dataflowr.github.io/website/ (fetched 2026-08-29T12:15:34.039024+00:00, sha edd0e49ce4e9)
- Data as of 2026-08-30T08:39:29.467469+00:00.